The high-frequency (HF) communication, commonly covering the frequency range between 3 and 30MHz, is an effective and important long-distance communication approach. Using the ionosphere as a natural high altitude reflector, trans-horizon HF radio transmission is possible with advantages such as high mobility,convenient deployment, strong survivability and fast network recon figuration. It finds widespread applications in various fields including military and emergency communications, and communication in remote regions and humanitarian projects.

Nevertheless, on one hand, usable HF frequencies are not easy to find and HF channels are often unstable due to the fluctuating altitude and density of the ionosphere.On the other hand, severe interference exists because of the crowded occupation of limited frequency resources,resulting in dif ficulties in finding desirable channels and maintaining established links. These challenges greatly restrict the efficiency of HF communications. Meanwhile, the requirements for transmitting high-speed services, serving more users and interconnecting with other kinds of networks are increasing. It is therefore vital to develop new technologies in finding usable frequencies and transmitting on these frequencies in an effective way.

To cope with these challenges and meet the requirements, modern HF communications evolve towards the three major tendencies: wideband, intelligent and integrated communications. As for wideband, it aims to transmit in channels wider than the traditional narrow band (usually 3kHz) to support wideband services such as image and video. As for intelligence, it focuses on intelligent techniques, e.g., in signal processing, frequency selection, networking and anti-jamming, to improve the efficiency and reliability of HF communications. As for integrated communications, it is important to merge the existing heterogeneous HF infrastructures into a platform, to enable HF communications interconnect with other kinds of networks.

Fortunately, huge progress has been made in wireless communication (beyond the 3-30MHz frequency band) areas in recent years. The plethora of techniques developed for wireless communications can possibly be explored and extended in the HF communications area,which can help enhancing its wideband, intelligent and integration abilities. Technology developments such as carrier aggregation, cooperative communications and MIMO will significantly enlarge the transmission band and enhance the capacity of HF communications. Cognitive radio, software defined networks and machine learning are promising techniques to realize intelligent HF communications. Integration of HF with heterogeneous communication systems, e.g., satellite communication networks, VHF communication networks and radar systems, requires designing new access network architectures. Several research groups around the world have been devoting efforts to the improvement of HF radio systems and techniques, and gathering of specific knowledge in multiple domains to achieve those improvements.

In response to the Call for Papers, we were pleased to receive a large number of manuscripts. The submissions underwent a rigorous peer review process, and finally only 8 papers were selected for publication in this special issue. These articles are expected to provide readers with relevant background information and techniques on the main issues of wideband, intelligent and integrated HF communications.

In the first article, “HF Communications: Past, Present, and Future” by Jinlong Wang, et al., the authors present a general tutorial on HF communications. By firstly presenting brief preliminaries on the unique features of HF communications, the technical evolution on the three generations of HF communication systems is reviewed. Further, the key challenges and research directions are highlighted.

The next two articles both focus on the issue of spectrum prediction in HF communications. In the second article, “A Spectrum Prediction-Based Frequency Band Pre-Selection over Deteriorating HF Electromagnetic Environment” by Xi Chen, et al., the authors focus on finding quality frequency in HF communications. By finding the correlations and predictability of HF frequency band in both time and frequency domain, a spectrum prediction-based frequency band pre-selection is developed to improve the efficiency of finding quality frequency.

On the other hand, the third article, “Deep Spectrum Prediction in High Frequency Communication Based on Temporal-Spectral Residual Network” by Ling Yu, et al., develops a deep learning based spectrum prediction scheme by simultaneously predicting multi-slot ahead states of multiple spectrum points within a period of time. The convolution neural network in this paper fuses the outputs of residual network modules for temporal-spectral prediction, which is combined with residual network modules to construct the deep temporal-spectral residual network.

In the fourth article, “Digital Channelization Technology for HF Communication Based on Fast Filter Bank”by Yixin Fan, et al., the feasibility and implementation of applying fast filter bank (FFB) in channelization is investigated. The authors analyze the butter fly structure of FFB similar with fast Fourier transform (FFT), in which prototype sub- filters is cascaded to achieve a low complexity. Then a pipelined structure of FFB is designed to achieve a balance between area and performance.

The following two articles study the issue of diversity in HF communication systems. In the fifth article, “High Frequency Communication Network with Diversity:System Structure and Key Enabling Techniques” by Kun Xu, et al., the authors focus on the HF communication network with diversity. Both simulation and field experimental results verify the performance advantages of diversity technology. The authors also provide a new structure and the key techniques of HF communication network with diversity.

Then, in the sixth article, “Exploring Channel Diversity in HF Communication Systems: A Matching-Potential Game Approach” by Wen Li, et al., the authors investigate the problem of joint channel and transmitter allocation in HF communication systems with channel diversity. A matching-potential game approach is proposed to achieve desirable solutions with low complexity.

The anti-jamming problems are investigated in the last two articles. The seventh article, “A Heterogeneous Information Fusion Deep Reinforcement Learning for Intelligent Frequency Selection of HF Communication”by Xin Liu, et al., adopts deep reinforcement learning to solve the problem of channel selection in the presence of crowded spectrum, time-varying channels, and malicious intelligent jamming. A heterogeneous information fusion deep reinforcement learning algorithm is designed for channel prediction, jamming avoidance and frequency channel selection.

The last article, “Throughput Analysis of Dynamic Spectrum Anti-Jamming Multiple-Access in HF Communication Systems” by Yichao Zhu, et al., focuses on the HF communication system, which consists of a center node and multiple user nodes. The authors propose a dynamic spectrum anti-jamming multiple access networking scheme. The throughput of the networking scheme is analyzed by taking into account the effect of error correction coding and transmission error of the spectrum hole information.

In closing, we would like to thank all the authors who submitted their work and the reviewers who devoted the time and effort to helping improve the quality of outstanding articles published in this special issue. We hope that all these articles provide readers with helpful information and stimulate more interests in the research and development of future HF communication systems.